mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-10 07:46:59 +00:00
ef14fb5b26
This commit represents a complete rework after pulling the latest changes from official ollama/ollama repository and re-applying Tesla K80 compatibility patches. ## Key Changes ### CUDA Compute Capability 3.7 Support (Tesla K80) - Added sm_37 (compute 3.7) to CMAKE_CUDA_ARCHITECTURES in CMakeLists.txt - Updated CMakePresets.json to include compute 3.7 in "CUDA 11" preset - Using 37-virtual (PTX with JIT compilation) for maximum compatibility ### Legacy Toolchain Compatibility - **NVIDIA Driver**: 470.256.02 (last version supporting Kepler/K80) - **CUDA Version**: 11.4.4 (last CUDA 11.x supporting compute 3.7) - **GCC Version**: 10.5.0 (required by CUDA 11.4 host_config.h) ### CPU Architecture Trade-offs Due to GCC 10.5 limitation, sacrificed newer CPU optimizations: - Alderlake CPU variant enabled WITHOUT AVX_VNNI (requires GCC 11+) - Still supports: SSE4.2, AVX, F16C, AVX2, BMI2, FMA - Performance impact: ~3-7% on newer CPUs (acceptable for K80 compatibility) ### Build System Updates - Modified ml/backend/ggml/ggml/src/ggml-cuda/CMakeLists.txt for compute 3.7 - Added -Wno-deprecated-gpu-targets flag to suppress warnings - Updated ml/backend/ggml/ggml/src/CMakeLists.txt for Alderlake without AVX_VNNI ### Upstream Sync Merged latest llama.cpp changes including: - Enhanced KV cache management with ISWA and hybrid memory support - Improved multi-modal support (mtmd framework) - New model architectures (Gemma3, Llama4, Qwen3, etc.) - GPU backend improvements for CUDA, Metal, and ROCm - Updated quantization support and GGUF format handling ### Documentation - Updated CLAUDE.md with comprehensive build instructions - Documented toolchain constraints and CPU architecture trade-offs - Removed outdated CI/CD workflows (tesla-k80-*.yml) - Cleaned up temporary development artifacts ## Rationale This fork maintains Tesla K80 GPU support (compute 3.7) which was dropped in official Ollama due to legacy driver/CUDA requirements. The toolchain constraint creates a deadlock: - K80 → Driver 470 → CUDA 11.4 → GCC 10 → No AVX_VNNI We accept the loss of cutting-edge CPU optimizations to enable running modern LLMs on legacy but still capable Tesla K80 hardware (12GB VRAM per GPU). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
33 lines
1.3 KiB
Diff
33 lines
1.3 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Daniel Hiltgen <daniel@ollama.com>
|
|
Date: Fri, 17 Oct 2025 14:17:00 -0700
|
|
Subject: [PATCH] report LoadLibrary failures
|
|
|
|
---
|
|
ggml/src/ggml-backend-reg.cpp | 12 ++++++++++++
|
|
1 file changed, 12 insertions(+)
|
|
|
|
diff --git a/ggml/src/ggml-backend-reg.cpp b/ggml/src/ggml-backend-reg.cpp
|
|
index f794d9cfa..3a855ab2e 100644
|
|
--- a/ggml/src/ggml-backend-reg.cpp
|
|
+++ b/ggml/src/ggml-backend-reg.cpp
|
|
@@ -118,6 +118,18 @@ static dl_handle * dl_load_library(const fs::path & path) {
|
|
SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
|
|
|
|
HMODULE handle = LoadLibraryW(path.wstring().c_str());
|
|
+ if (!handle) {
|
|
+ DWORD error_code = GetLastError();
|
|
+ std::string msg;
|
|
+ LPSTR lpMsgBuf = NULL;
|
|
+ DWORD bufLen = FormatMessageA(FORMAT_MESSAGE_ALLOCATE_BUFFER | FORMAT_MESSAGE_FROM_SYSTEM | FORMAT_MESSAGE_IGNORE_INSERTS,
|
|
+ NULL, error_code, MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT), (LPSTR)&lpMsgBuf, 0, NULL);
|
|
+ if (bufLen) {
|
|
+ msg = lpMsgBuf;
|
|
+ LocalFree(lpMsgBuf);
|
|
+ GGML_LOG_INFO("%s unable to load library %s: %s\n", __func__, path_str(path).c_str(), msg.c_str());
|
|
+ }
|
|
+ }
|
|
|
|
SetErrorMode(old_mode);
|
|
|